Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Hartunka/tiny_bert_km_5_v2_wnli")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/tiny_bert_km_5_v2_wnli")Quick Links
tiny_bert_km_5_v2_wnli
This model is a fine-tuned version of Hartunka/tiny_bert_km_5_v2 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6992
- Accuracy: 0.5493
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7123 | 1.0 | 3 | 0.7005 | 0.5634 |
| 0.7076 | 2.0 | 6 | 0.6992 | 0.5493 |
| 0.6978 | 3.0 | 9 | 0.7239 | 0.4366 |
| 0.6962 | 4.0 | 12 | 0.7077 | 0.3521 |
| 0.6953 | 5.0 | 15 | 0.7036 | 0.5070 |
| 0.6953 | 6.0 | 18 | 0.7111 | 0.4085 |
| 0.692 | 7.0 | 21 | 0.7194 | 0.2958 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1
- Downloads last month
- 3
Model tree for Hartunka/tiny_bert_km_5_v2_wnli
Base model
Hartunka/tiny_bert_km_5_v2Dataset used to train Hartunka/tiny_bert_km_5_v2_wnli
Evaluation results
- Accuracy on GLUE WNLIself-reported0.549
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/tiny_bert_km_5_v2_wnli")